© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57004
    Prev
    Next
    INDEX
    Explanations

    biological entities and their associated phenomena

    np_acts-logits-general · gemini-2.5-flash-lite

    terms related to biological and medical fields, particularly in the context of cellular, neural, or molecular processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stessi
    -1.41
    lography
    -1.27
     msglen
    -1.13
     млн
    -1.12
     some
    -1.10
    trucks
    -1.04
     any
    -1.03
     academia
    -1.02
    着一个
    -1.01
    смотра
    -1.00
    POSITIVE LOGITS
     types
    1.66
     categories
    1.54
     styles
    1.50
     technologies
    1.45
     forms
    1.43
     topics
    1.39
     and
    1.38
     situations
    1.38
     options
    1.37
     phenomena
    1.37
    Activations Density 0.399%

    No Known Activations